Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    place names and locations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    cities and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.75
    tagHelperRunner
    -0.71
     queſta
    -0.68
     يتيمه
    -0.65
    :✨
    -0.64
     للمعارف
    -0.64
    EndContext
    -0.63
    <unused42>
    -0.61
    <pad>
    -0.61
    <unused8>
    -0.61
    POSITIVE LOGITS
     Anaheim
    0.57
     Orlando
    0.49
     Orange
    0.45
     Disneyland
    0.43
    Orlando
    0.42
    idorm
    0.42
     orlando
    0.41
     naranja
    0.40
     апель
    0.39
     Anambra
    0.38
    Act Density 0.027%

    No Known Activations